© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7976
    Prev
    Next
    INDEX
    Explanations

    words related to encouragement and motivation, particularly in the context of community activities and development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.11
    0.5%
    255
    +0.11
    0.5%
    26
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.02
    643
    +0.11
    0.02
    421
    +0.09
    0.02
    Negative Logits
    stanbul
    -0.71
    abase
    -0.70
    ynski
    -0.69
    figured
    -0.68
    alian
    -0.68
    elt
    -0.66
    imposed
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    lain
    -0.65
    elle
    -0.65
    POSITIVE LOGITS
     experimentation
    0.91
     conversions
    0.84
     curiosity
    0.84
     creativity
    0.84
     disobedience
    0.82
     entrepreneurship
    0.81
     participation
    0.80
     innovation
    0.79
     compliance
    0.78
     laughter
    0.78
    Activations Density 0.051%

    No Known Activations